{"id":"https://openalex.org/W3149145721","doi":"https://doi.org/10.1007/s00607-021-00932-y","title":"A parallel text clustering method using Spark and hashing","display_name":"A parallel text clustering method using Spark and hashing","publication_year":2021,"publication_date":"2021-04-07","ids":{"openalex":"https://openalex.org/W3149145721","doi":"https://doi.org/10.1007/s00607-021-00932-y","mag":"3149145721"},"language":"en","primary_location":{"id":"doi:10.1007/s00607-021-00932-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00607-021-00932-y","pdf_url":null,"source":{"id":"https://openalex.org/S35593046","display_name":"Computing","issn_l":"0010-485X","issn":["0010-485X","1436-5057"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035735137","display_name":"Mohamed Aymen Ben HajKacem","orcid":"https://orcid.org/0000-0002-0161-6646"},"institutions":[{"id":"https://openalex.org/I4210140729","display_name":"Institut Sup\u00e9rieur de Gestion de Tunis","ror":"https://ror.org/04w9mdw91","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]},{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]}],"countries":["TN"],"is_corresponding":true,"raw_author_name":"Mohamed Aymen Ben HajKacem","raw_affiliation_strings":["LARODEC, Institut Sup\u00e9rieur de Gestion de Tunis, Universit\u00e9 de Tunis, Tunis, Tunisia"],"affiliations":[{"raw_affiliation_string":"LARODEC, Institut Sup\u00e9rieur de Gestion de Tunis, Universit\u00e9 de Tunis, Tunis, Tunisia","institution_ids":["https://openalex.org/I4210140729","https://openalex.org/I108714496"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006094657","display_name":"Chiheb-Eddine Ben N\u2019Cir","orcid":"https://orcid.org/0000-0003-4014-8264"},"institutions":[{"id":"https://openalex.org/I4210099699","display_name":"Jeddah University","ror":"https://ror.org/015ya8798","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210099699"]},{"id":"https://openalex.org/I4210140729","display_name":"Institut Sup\u00e9rieur de Gestion de Tunis","ror":"https://ror.org/04w9mdw91","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]},{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]}],"countries":["SA","TN"],"is_corresponding":false,"raw_author_name":"Chiheb-Eddine Ben N\u2019cir","raw_affiliation_strings":["College of Business, University of Jeddah, Jeddah, Saudi Arabia","LARODEC, Institut Sup\u00e9rieur de Gestion de Tunis, Universit\u00e9 de Tunis, Tunis, Tunisia"],"affiliations":[{"raw_affiliation_string":"College of Business, University of Jeddah, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I4210099699"]},{"raw_affiliation_string":"LARODEC, Institut Sup\u00e9rieur de Gestion de Tunis, Universit\u00e9 de Tunis, Tunis, Tunisia","institution_ids":["https://openalex.org/I4210140729","https://openalex.org/I108714496"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110248637","display_name":"Nadia Essoussi","orcid":null},"institutions":[{"id":"https://openalex.org/I108714496","display_name":"Tunis University","ror":"https://ror.org/02q1spa57","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496"]},{"id":"https://openalex.org/I4210140729","display_name":"Institut Sup\u00e9rieur de Gestion de Tunis","ror":"https://ror.org/04w9mdw91","country_code":"TN","type":"education","lineage":["https://openalex.org/I108714496","https://openalex.org/I4210140729"]}],"countries":["TN"],"is_corresponding":false,"raw_author_name":"Nadia Essoussi","raw_affiliation_strings":["LARODEC, Institut Sup\u00e9rieur de Gestion de Tunis, Universit\u00e9 de Tunis, Tunis, Tunisia"],"affiliations":[{"raw_affiliation_string":"LARODEC, Institut Sup\u00e9rieur de Gestion de Tunis, Universit\u00e9 de Tunis, Tunis, Tunisia","institution_ids":["https://openalex.org/I4210140729","https://openalex.org/I108714496"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035735137"],"corresponding_institution_ids":["https://openalex.org/I108714496","https://openalex.org/I4210140729"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":0.7955,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.7331524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"103","issue":"9","first_page":"2007","last_page":"2031"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9939000010490417,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8471589088439941},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8354997634887695},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.62474125623703},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.6209670901298523},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5660187602043152},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.5645730495452881},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5053430199623108},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.49138060212135315},{"id":"https://openalex.org/keywords/brown-clustering","display_name":"Brown clustering","score":0.4725764989852905},{"id":"https://openalex.org/keywords/clustering-high-dimensional-data","display_name":"Clustering high-dimensional data","score":0.46733105182647705},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4498153030872345},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.44387441873550415},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4411028027534485},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.4134232699871063},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.39566469192504883},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.3853093981742859},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.3782498240470886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2698213458061218},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20751407742500305}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8471589088439941},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8354997634887695},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.62474125623703},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.6209670901298523},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5660187602043152},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.5645730495452881},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5053430199623108},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.49138060212135315},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.4725764989852905},{"id":"https://openalex.org/C184509293","wikidata":"https://www.wikidata.org/wiki/Q5136711","display_name":"Clustering high-dimensional data","level":3,"score":0.46733105182647705},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4498153030872345},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.44387441873550415},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4411028027534485},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.4134232699871063},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.39566469192504883},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.3853093981742859},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.3782498240470886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2698213458061218},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20751407742500305},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00607-021-00932-y","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00607-021-00932-y","pdf_url":null,"source":{"id":"https://openalex.org/S35593046","display_name":"Computing","issn_l":"0010-485X","issn":["0010-485X","1436-5057"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W29295388","https://openalex.org/W1488461535","https://openalex.org/W1596213861","https://openalex.org/W1598064945","https://openalex.org/W1651093245","https://openalex.org/W1833785989","https://openalex.org/W1960685374","https://openalex.org/W1980428340","https://openalex.org/W1992419399","https://openalex.org/W2007855409","https://openalex.org/W2040058125","https://openalex.org/W2043819533","https://openalex.org/W2044459073","https://openalex.org/W2047852079","https://openalex.org/W2058990119","https://openalex.org/W2069564486","https://openalex.org/W2079392363","https://openalex.org/W2080234606","https://openalex.org/W2085927849","https://openalex.org/W2089497633","https://openalex.org/W2090898720","https://openalex.org/W2107117509","https://openalex.org/W2111537739","https://openalex.org/W2112490010","https://openalex.org/W2113359929","https://openalex.org/W2116762767","https://openalex.org/W2121456247","https://openalex.org/W2126623642","https://openalex.org/W2127218421","https://openalex.org/W2140190241","https://openalex.org/W2140321362","https://openalex.org/W2142522063","https://openalex.org/W2142838865","https://openalex.org/W2144743826","https://openalex.org/W2147152072","https://openalex.org/W2169446650","https://openalex.org/W2169541495","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2526108798","https://openalex.org/W2557792717","https://openalex.org/W2733722625","https://openalex.org/W2735941455","https://openalex.org/W2767606292","https://openalex.org/W2772326905","https://openalex.org/W2775797061","https://openalex.org/W2898602371","https://openalex.org/W2910370510","https://openalex.org/W2911803837","https://openalex.org/W2964454757","https://openalex.org/W2995564009","https://openalex.org/W2998388915","https://openalex.org/W3011290429","https://openalex.org/W3039717108","https://openalex.org/W4235522617"],"related_works":["https://openalex.org/W2163563073","https://openalex.org/W3140018618","https://openalex.org/W46244302","https://openalex.org/W2187529160","https://openalex.org/W2118873177","https://openalex.org/W2414630753","https://openalex.org/W4226410418","https://openalex.org/W3217529043","https://openalex.org/W4321146132","https://openalex.org/W2282393731"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
